Classifications

• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
  • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
  • G06F16/24—Querying
  • G06F16/245—Query processing
  • G06F16/2457—Query processing with adaptation to user needs
  • G06F16/24578—Query processing with adaptation to user needs using ranking
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
  • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
  • G06F16/24—Querying
  • G06F16/248—Presentation of query results
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
  • G06F16/90—Details of database functions independent of the retrieved data types
  • G06F16/95—Retrieval from the web
  • G06F16/951—Indexing; Web crawling techniques
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
  • G06F16/90—Details of database functions independent of the retrieved data types
  • G06F16/95—Retrieval from the web
  • G06F16/953—Querying, e.g. by the use of web search engines
  • G06F16/9535—Search customisation based on user profiles and personalisation
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
  • G06F16/90—Details of database functions independent of the retrieved data types
  • G06F16/95—Retrieval from the web
  • G06F16/953—Querying, e.g. by the use of web search engines
  • G06F16/9538—Presentation of query results

Definitions

• Search engines are widely used in today's society. Users typically provide search terms and receive the search results. The results are ranked by the search engine, and are provided to the user according to the ranking. Usually, the highest ranked item (i.e. that item most likely to match the user's search term) is displayed most prominently. Users may then be able to sort these search results from newest to oldest, cheapest to most expensive, closest by to furthest away, etc. The sorting, however, has no effect on how the search results are initially ranked by the search engine.
• Embodiments described herein are directed to dynamically tuning search result rankings to control how the search results are presented in a user interface and to dynamically updating search result rankings based on tuning inputs.
• a computer system receives search results, where each search result has associated search result attributes. The search results are displayed within a user interface according to each search result's determined ranking. The computer system then receives a tuning input at the user interface. The tuning input indicates that a search result ranking model is to be adjusted for various specified search result attributes. Moreover, the search result ranking model determines how each search result is ranked. The computer system then dynamically updates the displayed search results as the search result ranking model is tuned for the specified search result attributes. The dynamic updating includes repositioning, adding and removing search results according to the determined ranking for each search result.
• a computer system dynamically updates search result rankings based on tuning inputs.
• the computer system provides search results which are ranked according to a search results ranking model, where each search result has associated search result attributes.
• the computer system receives a tuning input indicating that the search result ranking model is to be adjusted for specified search result attributes, where the search result ranking model determines how each search result is ranked.
• the computer system then dynamically updates the provided search results according to the updated ranking based on the tuning input.
• the user interface that displays the search results is dynamically updated to reflect the changed search results rankings.
• Figure 1 illustrates a computer architecture in which embodiments described herein may operate including dynamically tuning search result rankings to control how the search results are presented in a user interface.
• Figure 2 illustrates a flowchart of an example method for dynamically tuning search result rankings to control how the search results are presented in a user interface.
• Figure 3 illustrates a flowchart of an example method for dynamically updating search result rankings based on tuning inputs.
• Figure 4 illustrates an embodiment in which search results are dynamically updated based on a tuning input.
• Figure 5 illustrates an embodiment of a user interface in which controls are provided for providing tuning inputs.
• Embodiments described herein are directed to dynamically tuning search result rankings to control how the search results are presented in a user interface and to dynamically updating search result rankings based on tuning inputs.
• a computer system receives search results, where each search result has associated search result attributes. The search results are displayed within a user interface according to each search result's determined ranking. The computer system then receives a tuning input at the user interface. The tuning input indicates that a search result ranking model is to be adjusted for various specified search result attributes. Moreover, the search result ranking model determines how each search result is ranked. The computer system then dynamically updates the displayed search results as the search result ranking model is tuned for the specified search result attributes.
• a computer system dynamically updates search result rankings based on tuning inputs.
• the computer system provides search results which are ranked according to a search results ranking model, where each search result has associated search result attributes.
• the computer system receives a tuning input indicating that the search result ranking model is to be adjusted for specified search result attributes, where the search result ranking model determines how each search result is ranked.
• the computer system then dynamically updates the provided search results according to the updated ranking based on the tuning input. As such, the user interface that displays the search results is dynamically updated to reflect the changed search results rankings.
• Computing systems are now increasingly taking a wide variety of forms.
• Computing systems may, for example, be handheld devices, appliances, laptop computers, desktop computers, mainframes, distributed computing systems, or even devices that have not conventionally been considered a computing system.
• the term "computing system” is defined broadly as including any device or system (or combination thereof) that includes at least one physical and tangible processor, and a physical and tangible memory capable of having thereon computer-executable instructions that may be executed by the processor.
• a computing system may be distributed over a network environment and may include multiple constituent computing systems.
• a computing system 101 A typically includes at least one processing unit 102A and memory 103 A.
• the memory 103 A may be physical system memory, which may be volatile, non-volatile, or some combination of the two.
• the term "memory” may also be used herein to refer to non-volatile mass storage such as physical storage media. If the computing system is distributed, the processing, memory and/or storage capability may be distributed as well.
• executable module can refer to software objects, routings, or methods that may be executed on the computing system.
• the different components, modules, engines, and services described herein may be implemented as objects or processes that execute on the computing system (e.g., as separate threads).
• embodiments are described with reference to acts that are performed by one or more computing systems. If such acts are implemented in software, one or more processors of the associated computing system that performs the act direct the operation of the computing system in response to having executed computer- executable instructions.
• such computer-executable instructions may be embodied on one or more computer-readable media that form a computer program product.
• An example of such an operation involves the manipulation of data.
• the computer-executable instructions (and the manipulated data) may be stored in the memory 103 A of the computing system 101 A.
• Computing system 101 A may also contain communication channels that allow the computing system 101 A to communicate with other message processors over a wired or wireless network.
• Embodiments described herein may comprise or utilize a special-purpose or general-purpose computer system that includes computer hardware, such as, for example, one or more processors and system memory, as discussed in greater detail below.
• the system memory may be included within the overall memory 103 A.
• the system memory may also be referred to as "main memory”, and includes memory locations that are addressable by the at least one processing unit 102A over a memory bus in which case the address location is asserted on the memory bus itself.
• System memory has been traditional volatile, but the principles described herein also apply in circumstances in which the system memory is partially, or even fully, non-volatile.
• Embodiments within the scope of the present invention also include physical and other computer-readable media for carrying or storing computer-executable instructions and/or data structures.
• Such computer-readable media can be any available media that can be accessed by a general-purpose or special-purpose computer system.
• Computer-readable media that store computer-executable instructions and/or data structures are computer storage media.
• Computer-readable media that carry computer-executable instructions and/or data structures are transmission media.
• embodiments of the invention can comprise at least two distinctly different kinds of computer-readable media: computer storage media and transmission media.
• Computer storage media are physical hardware storage media that store computer- executable instructions and/or data structures.
• Physical hardware storage media include computer hardware, such as RAM, ROM, EEPROM, solid state drives (“SSDs”), flash memory, phase-change memory (“PCM”), optical disk storage, magnetic disk storage or other magnetic storage devices, or any other hardware storage device(s) which can be used to store program code in the form of computer-executable instructions or data structures, which can be accessed and executed by a general-purpose or special-purpose computer system to implement the disclosed functionality of the invention.
• Transmission media can include a network and/or data links which can be used to carry program code in the form of computer-executable instructions or data structures, and which can be accessed by a general-purpose or special-purpose computer system.
• a "network" is defined as one or more data links that enable the transport of electronic data between computer systems and/or modules and/or other electronic devices.
• program code in the form of computer-executable instructions or data structures can be transferred automatically from transmission media to computer storage media (or vice versa).
• computer- executable instructions or data structures received over a network or data link can be buffered in RAM within a network interface module (e.g., a "NIC"), and then eventually transferred to computer system RAM and/or to less volatile computer storage media at a computer system.
• a network interface module e.g., a "NIC”
• NIC network interface module
• computer storage media can be included in computer system components that also (or even primarily) utilize transmission media.
• Computer-executable instructions comprise, for example, instructions and data which, when executed at one or more processors, cause a general-purpose computer system, special-purpose computer system, or special-purpose processing device to perform a certain function or group of functions.
• Computer-executable instructions may be, for example, binaries, intermediate format instructions such as assembly language, or even source code.
• Cloud computing environments may be distributed, although this is not required. When distributed, cloud computing environments may be distributed internationally within an organization and/or have components possessed across multiple organizations.
• cloud computing is defined as a model for enabling on-demand network access to a shared pool of configurable computing resources (e.g., networks, servers, storage, applications, and services). The definition of “cloud computing” is not limited to any of the other numerous advantages that can be obtained from such a model when properly deployed.
• system architectures described herein can include a plurality of independent components that each contribute to the functionality of the system as a whole.
• This modularity allows for increased flexibility when approaching issues of platform scalability and, to this end, provides a variety of advantages.
• System complexity and growth can be managed more easily through the use of smaller-scale parts with limited functional scope.
• Platform fault tolerance is enhanced through the use of these loosely coupled modules.
• Individual components can be grown incrementally as business needs dictate. Modular development also translates to decreased time to market for new functionality. New functionality can be added or subtracted without impacting the core system.
• FIG. 1 illustrates a computer architecture 100 in which at least one embodiment may be employed.
• Computer architecture 100 includes computer systems 101A and 101B.
• Computer systems 101 A and 10 IB may be any type of local or distributed computer systems, including cloud computing systems.
• the computer systems 101 A and 10 IB may each be the same type of computer system, or may be different types of computer systems.
• Each system includes various modules for performing different functions.
• computer system 101 A includes a communications module 104A which receives input from user 105 and passes it on to various internal modules and/or to the communications module 104B of computer system 101B.
• the communications modules 104A/104B may be used to communicate with substantially any number of other computer systems, using any wired or wireless means of digital or analog communication.
• the inputs received by communications module 104A may include search terms or attributes 106.
• the term “attribute” or “search attribute” may include or encompass search terms, but may also include other values or items beyond a simple search term.
• a "search term”, as is generally understood, is a word, phrase, or symbol that is to be searched against a database.
• search results may include rankings 110 which may be shown or not shown.
• the search results are displayed to the user in user interface 108 according to the ranking 110 established by the computer system that performed the search (e.g. 101B).
• the search results would include those results that were most relevant to the search term "shoes", with the most relevant result being displayed highest or most prominently in the user interface.
• the searches performed by the user 105 are for web pages, software applications, documents or other internet results. In other cases, the searches may be performed on backend computer systems within a corporation or other entity. In either case, the search results 109 are displayed according to a ranking 110. This ranking may be determined in a variety of different manners, as will be explained further below. Regardless of how the ranking is determined, the user 105 may desire to change the ranking. For instance, user 105 may be the owner or manager of a web site. As an owner or manager, the user would have access to site-related data such as search terms input by the website users. The user may view the search terms, or view the search terms input by the website user that led the website user to the owner/manager's website. The owner/manager 105 may determine that the search results shown to the website user are suboptimal. In response, the owner/manager 105 may wish to change how the search results 109 are ranked and/or how the search results are displayed to the website user.
• the owner/manager 105 may thus provide a tuning input 107 that tunes various search result attributes 112A of the search result ranking model 111 A.
• the search result ranking model 111A may dynamically re-rank the search results, and the user interface 108 may dynamically update the displayed search results 109D to reflect the new rankings.
• results that showed up high on the list may drop to lower spots or may disappear entirely from the list of displayed search results.
• Other search results that were previously not displayed may be brought to the forefront or even the top of the displayed results 109D. This process is referred to as "real-time search tuning" herein.
• Real-time search tuning allows users (e.g. website owner/manager 105) to take search results and adjust them based on business or other objectives. For example, an ecommerce retailer may wish to allow website users to search over their product table based on entered search terms. In a tradition search system, results relevant to these terms will be returned. With real-time search tuning, the retailer can tune various search result attributes 112A, including supply weighting boosts in order to change the ranking of the search results.
• the user interface 108 may include visual dials, slider bars, switches, drop-down boxes, or other means for adjusting search result attribute parameters. As the user adjusts the attribute parameters, the user will be able to (substantially) instantly see, in real-time, the results of these adjustments.
• the owner/manager may wish to increase or "boost" the relevancy weighting of a certain product or search result so that higher margin product items appear higher in the search results.
• the search term 106 matches a certain search result attribute directly or indirectly, to move that search result up or down on the list of displayed search results 108.
• the user can use various knob, dials or other means (e.g. those shown in the user interface of Figure 5) to tune search result attributes and see the results of their tuning in real-time, as search results move up or down the list of displayed items, or are added to or removed from the list of displayed items entirely.
• Method 200 includes an act of receiving one or more search results, the search results being displayed within a user interface according to each search result's determined ranking, each search result having one or more associated search result attributes (act 210).
• communications module 104A of computer system 101A may receive search results 109 from the communications module 104B of computer system 101B.
• the search results 109 may be the result of the search processing module 115 having received one or more search terms or attributes 106, and having processed the search.
• the search results 109 may be displayed in user interface 108 according to ranking 110.
• the ranking may be determined by the search processing module 115 and/or the search result ranking model 11 lA/B.
• the search result ranking model may be on computer system 101 A or on computer system 101B.
• the search result ranking 110 may be modified by the model 11 IB on computer system 10 IB, or by the model 111 A on computer system 101 A.
• the search result ranking may be associated with the specified search term.
• the search processing module 115 may locate bands, albums, songs, or other items related to rock music.
• the search processing module will then rank the search results 109 according to one or more ranking algorithms. This ranking may then be changed by changing search result attributes 112A within the search result ranking model, as will be explained further below.
• the search terms or attributes for which the corresponding search result attributes are to be adjusted may be provided by a user, a computer system, a software application or any other entity. Thus, the search may have been performed at the request of another computer system, software application, user or other entity.
• Method 200 includes an act of receiving a tuning input at the user interface, the tuning input indicating that a search result ranking model is to be adjusted for one or more specified search result attributes, the search result ranking model determining how each search result is ranked (act 220).
• computer system 101 A may receive tuning input 107 from user 105 at user interface 108.
• the tuning input 107 indicates that one or more search result attributes 112A within the search result ranking model 111A are to be adjusted.
• the adjusting may include increasing or decreasing the importance of a certain term, increasing or decreasing the importance of a certain search result, or type of search results, or changing some other factor. Such factors may be referred to herein as "weighting" factors.
• the owner or manager of a music website may wish to increase the weighting for certain search results if the search term or attribute 106 matches certain columns of information. For instance, if the search term "rock music" matches directly to a genre column, search results with the directly matching column would be weighted higher. If the term "rock music” only matched an "album description” column, that search result would be weighted lower.
• the owner/manager could increase the search result weighting for those items so that they appear higher in the displayed search results 109D in the user interface 108.
• Method 200 further includes an act of dynamically updating the displayed search results as the search result ranking model is tuned for the specified search result attributes, the dynamic updating including at least one of repositioning, adding and removing search results according to the determined ranking for each search result (act 230).
• the displayed search results 108 in user interface 108 may be dynamically updated as the search result ranking model 110 is tuned.
• a user may use a virtual tuning knob 503A to adjust search result attribute 504A.
• the knob may be changed from zero to ten, whereby the search results of Figure 4 may be dynamically updated.
• search results 402A, 402B, 402C and 402D may be displayed in the initial user interface 401A (i.e.
• search result 402C may be moved to the top of the list (i.e. ranked highest), new search result 402E is listed next, search result 402A comes next (after falling two spots), and search result 402D remains in the same position. Accordingly, as the user tunes the knob 503A to adjust search result attribute 503 A, search results may be reordered, added or removed from the displayed search results in real time, as the know is moved up or down.
• slider bar 503B may be used to adjust search result attribute 504B from low to high
• drop-down menu 503C may be used to adjust search result attribute 504C, along with one or more values 505A and/or 505B.
• the owner or manager of a website or of another data store may thus tweak and change how search results are ranked and ultimately presented to end users.
• the tuning input (via UI elements 503A-C or via some other text- based or gesture-based control) thus modifies the search result ranking model 111A so that weight is added to or removed from search results according to the tuning input.
• the search result ranking model 111A itself may be configured to divide the search result attributes 112A into weights and scoring functions, and further divide the scoring functions into various measures including freshness, distance, magnitude, tags or other measures that are used in forming or modifying the ranking 110.
• Some embodiments may allow users (e.g. data owners or managers) to store sets of search result ranking model settings as a tuning profile.
• This tuning profile may correspond to a specified search term or attribute 106.
• the search result ranking model settings of that profile will automatically be applied.
• the owner's created settings profile i.e. the tuning profile for that search term will be applied to the search results, and the search results will be ranked according to the tuning profile.
• tuning profile may correspond to a specific search term or attribute
• a tuning profile may correspond to and be applied to searches provided by certain users, certain groups of users, certain groups of search terms, or to other designated entities.
• search terms when search terms are received from that user or group of users or is part of a specified group of search terms, the profile (or profiles) corresponding to that group will be applied automatically within the search result ranking model 111 A, and the displayed search results 109D will be displayed according to the settings provided in the appropriate profile.
• FIG. 3 a flowchart is illustrated of a method 300 for dynamically updating search result rankings based on tuning inputs. The method 300 will now be described with frequent reference to the components and data of environment 100 of Figure 1.
• Method 300 includes an act of providing one or more search results, the search results being ranked according to a search results ranking model, each search result having one or more associated search result attributes (act 310).
• search processing module 115 of computer system 10 IB may provide search results 109 which are ranked according to ranking 110.
• Method 300 next includes an act of receiving a tuning input indicating that the search result ranking model is to be adjusted for one or more specified search result attributes, the search result ranking model determining how each search result is ranked (act 320).
• the tuning input 107 may be received from computer system 101A or directly from user 105.
• the tuning input specifies which search result attributes 112B are to be adjusted within the search result ranking model 11 IB.
• Method 300 further includes an act of dynamically updating the provided search results according to the updated ranking based on the tuning input, such that the user interface displaying the search results is dynamically updated to reflect the changed search results rankings (act 330).
• the computer system 101B may continually provide the user interface 108 with dynamically updated, properly ranked search results.
• a user e.g. data owner/manager 105 makes a search request from a client side application (having a user interface which may be the same as or different than user interface 108). This request goes to a backend server (e.g. computer system 10 IB) which receives this request and passes it on to the search result ranking model 11 IB.
• a backend server e.g. computer system 10 IB
• the search request may be handled in a default manner in which no custom tuning of the search index is performed, so that the request is processed according to the search processing module's ranking algorithms.
• the search results are passed back from the search processing module 115 to the client side application where the results are then displayed to the user in user interface 108.
• An owner, manager or administrator who wants to "tune" the search results ranking 110 may tune search result attributes 112B directly, or may configure tuning profiles for a given search term or attribute.
• the administrator or other user may enter in a search term that they wish to tune.
• This tuning request is sent to computer system 101B which receives this request and passes it on to the search result ranking model 11 IB.
• the search result ranking model ranks the search results and sends the results 109 to the computer system 101 A where they are displayed, along with various controls (as shown in Figure 5) for tuning the search results.
• the change is passed to the backend server (e.g. computer system 10 IB) .
• the administrator, owner or manager may continue to make changes to the tuning profile until they are happy with the results.
• the changes to the tuning profile are saved. From that point on, incoming search terms matching the tuning profile will have the tuning profile applied so that the search results are ranked according to the administrator-designed profile.
• intermediate configuration states are possible. These intermediate states allow users to try tuning modifications without having to actually save and/or implement them.
• the user 105 makes a search request from their client side application via user interface 108.
• This search request goes to the backend server (i.e. computer system 101B) which receives this request and passes it on to the search result ranking model 11 IB.
• the backend server i.e. computer system 101B
• the tuning profile will be used to alter the rankings of the search engine results.
• the user 105 will provide the name of the tuning profile in the search request.
• the search results 109 are passed from the backend server to the computer system 101 A where they are displayed on the user interface 108.
• the search results are displayed according to the ranking resulting from the tuning profile applied by the search result ranking model 11 IB.
• the backend server 10 IB listens for input parameters from the client side user interface 108. These parameters (i.e. tuning input 107) will describe the changes that are to be made to the scoring profiles for the search results.
• tuning input 107 i.e. tuning input 107
• the administrator wanted to boost one search field (e.g., Title) higher than another field (e.g., Description) such that when a search term is entered and the search term was found in the Title column, this would give a higher weighted boost to the ranking score applied to that row than if the term was found in the Description field. This allows items that are of more importance to be boosted higher in the search results.
• the user interface 108 would visually and dynamically allow the administrator, data owner or manager to choose the columns where this boosting could be applied and the amount at which those columns could be boosted. These tuning parameters may then be sent to the backend server 10 IB, which would interpret these parameters and convert them into scoring profile expressions that are applied by the search result ranking model dynamically at runtime.
• the tuning parameters are converted into scoring expressions. For each field weight that is specified, a term-query is constructed that includes a weight factor in it. As such, when a search result is found producing a non-zero score, the weighting for that search result is adjusted by the boost factor.
• the initial score comes from the statistical properties of the data corpus and the search terms.
• For each scoring function freshness, magnitude, etc. the value in the matching document is interpolated into the range provided by configuration, using an easing function also provided by configuration data (e.g. logarithmic, quadratic, linear, constant). The resulting number is a boost factor that is also applied to the search result.
• Each weighting boost is combined into a final boost or weighting value that is used to adjust the weighting score using an aggregate function such as sum, average, max, etc.
• scoring profiles that could be tuned with using the user interface 108 include (but are not limited to): "freshness”, where newer (or older) search results get a boost relative to the current date, and "magnitude", where documents get a boost when they are closer to one side of the range (e.g. star rating as numbers 1-5, margin as dollar amount or percent amount).
• freshness where newer (or older) search results get a boost relative to the current date
• magnitude where documents get a boost when they are closer to one side of the range
• star rating e.g. star rating as numbers 1-5, margin as dollar amount or percent amount.
• a search term or attribute 106 is entered by a website or other user (e.g. data owner/manager 105), and when the owner/manager has provided a tuning input 107, that tuning input may be mapped to the search algorithms used by the search processing module 115, such that the search is performed using the tuning input, as opposed to applying the tuning input 107 after the search has been performed. In such cases, the search results will be correctly displayed initially, without needing to be arranged according to an updated ranking.
• the backend server may provide suggested changes to a search user based on context information associated with the user. For example, if the user is a returning user, or if the computer system 101B otherwise determines that the user has purchased similar items at another website, for example, the computer system 10 IB may provide hints or suggested changes to the user to assist the user in providing an optimal search term and/or an optimal tuning input 107.
• the tuning input may include defining interpolations for various search result attributes. The interpolations indicate the rate at which search result ranking is to change based on the contents of the search results. This rate of change may be linear, even, logarithmic or some other rate of change.
• the computer system 101B may provide suggestions for a given search term, based on prior tuning inputs and/or previously stored tuning profiles.
• other search result attributes are automatically updated. For instance, if a search result attribute is changed when a tuning input is applied to a value associated with the search term (e.g. search results are tuned to show high- star- value items), other related search result attributes (e.g. freshness) may also be automatically updated. In this manner, a user may be able to dynamically tune search results to achieve a desired search result ranking.
• methods, systems and computer program products are provided which dynamically tune search result rankings to control how the search results are presented in a user interface. Moreover, methods, systems and computer program products are provided which dynamically update search result rankings based on tuning inputs.

Landscapes

• Engineering & Computer Science (AREA)
• Theoretical Computer Science (AREA)
• Databases & Information Systems (AREA)
• Data Mining & Analysis (AREA)
• Physics & Mathematics (AREA)
• General Engineering & Computer Science (AREA)
• General Physics & Mathematics (AREA)
• Computational Linguistics (AREA)
• Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
• User Interface Of Digital Computer (AREA)

Applications Claiming Priority (2)

Publications (1)

Family

ID=51932600

Family Applications (1)

Country Status (7)

Families Citing this family (27)

Family Cites Families (39)

• 2013
  • 2013-11-01 US US14/070,004 patent/US9760608B2/en active Active
• 2014
  • 2014-10-31 WO PCT/US2014/063466 patent/WO2015066497A1/en active Application Filing
  • 2014-10-31 BR BR112016009252A patent/BR112016009252A8/pt not_active Application Discontinuation
  • 2014-10-31 CN CN201480060870.6A patent/CN106415529A/zh active Pending
  • 2014-10-31 RU RU2016116911A patent/RU2663478C2/ru active
  • 2014-10-31 EP EP14800210.8A patent/EP3063677A1/en not_active Ceased
  • 2014-10-31 JP JP2016526124A patent/JP6498191B2/ja active Active
• 2017
  • 2017-09-01 US US15/694,514 patent/US20170364522A1/en not_active Abandoned
• 2019
  • 2019-03-12 JP JP2019044551A patent/JP6802870B2/ja active Active

Non-Patent Citations (2)

Also Published As

Similar Documents

Legal Events